Skip to content

Benchmark

UzLiB fill-in accuracy

Multilingual benchmarks compare model performance across languages. Higher scores are better.

Models measured
74
Scores recorded
74
Sources
1
IQ weight
1.36

Score distribution

0.449
Mean
0.423
Median
0.156
Std dev
0.269
10th percentile
0.692
90th percentile
0.173
Min
0.1730.808
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 1.36 for chat models, measured over 73 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.

Leaderboard

#ModelScore
1Gemini 4 Argontemperature: 1.0, top_p: 0.95· UzLiB Uzbek linguistic benchmark data docs0.808
2Gemini 4 Carbontemperature: 1.0, top_p: 0.95· UzLiB Uzbek linguistic benchmark data docs0.789
3Gemini 4 Neontemperature: 1.0, top_p: 0.95· UzLiB Uzbek linguistic benchmark data docs0.789
4Gemini 3.1 Pro Previewtemperature: 1.0, top_p: 0.95· UzLiB Uzbek linguistic benchmark data docs0.75
5Gemini 3 Pro Previewtemperature: 1.0, top_p: 0.95· UzLiB Uzbek linguistic benchmark data docs0.731
6Claude Opus 5.5temperature: 1.0, top_p: 0.95· UzLiB Uzbek linguistic benchmark data docs0.712
7Gemini 3 Flashtemperature: 1.0, top_p: 0.95· UzLiB Uzbek linguistic benchmark data docs0.692
8Gemini 3.7 Flashtemperature: 1.0, top_p: 0.95· UzLiB Uzbek linguistic benchmark data docs0.692
9Gemini 4 Hydrogentemperature: 1.0, top_p: 0.95· UzLiB Uzbek linguistic benchmark data docs0.692
10Muse Spark 1.3temperature: 1.0, top_p: 0.95· UzLiB Uzbek linguistic benchmark data docs0.692
11Gemini 3.5 Flashtemperature: 1.0, top_p: 0.95· UzLiB Uzbek linguistic benchmark data docs0.654
12Claude Sonnet 5.5temperature: 1.0, top_p: 0.95· UzLiB Uzbek linguistic benchmark data docs0.635
13DeepSeek V4.1 Flashtemperature: 1.0, top_p: 0.95· UzLiB Uzbek linguistic benchmark data docs0.596
14Claude Sonnet 4.6temperature: 1.0, top_p: 0.95· UzLiB Uzbek linguistic benchmark data docs0.577
15GPT-6 Lunatemperature: 1.0, top_p: 0.95· UzLiB Uzbek linguistic benchmark data docs0.577
16DeepSeek V4 Protemperature: 1.0, top_p: 0.95· UzLiB Uzbek linguistic benchmark data docs0.558
17Gemini 2.0 Flashtemperature: 1.0, top_p: 0.95· UzLiB Uzbek linguistic benchmark data docs0.558
18Gemini 2.5 Protemperature: 1.0, top_p: 0.95· UzLiB Uzbek linguistic benchmark data docs0.558
19GPT 4otemperature: 1.0, top_p: 0.95· UzLiB Uzbek linguistic benchmark data docs0.558
20DeepSeek V4 Flashtemperature: 1.0, top_p: 0.95· UzLiB Uzbek linguistic benchmark data docs0.539
21Claude Sonnet 5temperature: 1.0, top_p: 0.95· UzLiB Uzbek linguistic benchmark data docs0.519
22GLM 5.3temperature: 1.0, top_p: 0.95· UzLiB Uzbek linguistic benchmark data docs0.519
23GPT 5.2temperature: 1.0, top_p: 0.95· UzLiB Uzbek linguistic benchmark data docs0.519
24Ling 3.0 Flashtemperature: 1.0, top_p: 0.95· UzLiB Uzbek linguistic benchmark data docs0.519
25GPT OSS 120Btemperature: 1.0, top_p: 0.95· UzLiB Uzbek linguistic benchmark data docs0.5
26Claude Sonnet 3.7temperature: 1.0, top_p: 0.95· UzLiB Uzbek linguistic benchmark data docs0.481
27DeepSeek V3temperature: 1.0, top_p: 0.95· UzLiB Uzbek linguistic benchmark data docs0.481
28Gemini 2.5 Flashtemperature: 1.0, top_p: 0.95· UzLiB Uzbek linguistic benchmark data docs0.481
29GLM 5.3 Flashtemperature: 1.0, top_p: 0.95· UzLiB Uzbek linguistic benchmark data docs0.481
30Gemma 4 31B ITtemperature: 1.0, top_p: 0.95· UzLiB Uzbek linguistic benchmark data docs0.462
31GPT-5.6 Lunatemperature: 1.0, top_p: 0.95· UzLiB Uzbek linguistic benchmark data docs0.462
32Mercury 2.5temperature: 1.0, top_p: 0.95· UzLiB Uzbek linguistic benchmark data docs0.462
33Gemini 2.0 Flash Litetemperature: 1.0, top_p: 0.95· UzLiB Uzbek linguistic benchmark data docs0.442
34Gemma 4 26B A4Btemperature: 1.0, top_p: 0.95· UzLiB Uzbek linguistic benchmark data docs0.442
35Jev 1.13.0temperature: 1.0, top_p: 0.95· UzLiB Uzbek linguistic benchmark data docs0.442
36Qwen3.5 397B A17Btemperature: 1.0, top_p: 0.95· UzLiB Uzbek linguistic benchmark data docs0.442
37Claude Opus 4.5temperature: 1.0, top_p: 0.95· UzLiB Uzbek linguistic benchmark data docs0.423
38GPT 5temperature: 1.0, top_p: 0.95· UzLiB Uzbek linguistic benchmark data docs0.423
39Qwen3 8Btemperature: 1.0, top_p: 0.95· UzLiB Uzbek linguistic benchmark data docs0.423
40Qwen3.5 27Btemperature: 1.0, top_p: 0.95· UzLiB Uzbek linguistic benchmark data docs0.413
41Claude Sonnet 4temperature: 1.0, top_p: 0.95· UzLiB Uzbek linguistic benchmark data docs0.404
42Grok 4.3temperature: 1.0, top_p: 0.95· UzLiB Uzbek linguistic benchmark data docs0.404
43Qwen3.5 122B-A10Btemperature: 1.0, top_p: 0.95· UzLiB Uzbek linguistic benchmark data docs0.404
44C4AI Command A 03 2025temperature: 1.0, top_p: 0.95· UzLiB Uzbek linguistic benchmark data docs0.385
45Qwen3.5 35B A3Btemperature: 1.0, top_p: 0.95· UzLiB Uzbek linguistic benchmark data docs0.385
46GPT-4o minitemperature: 1.0, top_p: 0.95· UzLiB Uzbek linguistic benchmark data docs0.365
47Grok 3temperature: 1.0, top_p: 0.95· UzLiB Uzbek linguistic benchmark data docs0.365
48Phi 4temperature: 1.0, top_p: 0.95· UzLiB Uzbek linguistic benchmark data docs0.365
49Qwen3 235B A22B Instruct 2507temperature: 1.0, top_p: 0.95· UzLiB Uzbek linguistic benchmark data docs0.365
50Qwen3 32Btemperature: 1.0, top_p: 0.95· UzLiB Uzbek linguistic benchmark data docs0.365

Showing 1–50 of 74 results.

Data credits: UzLiB, Tahrirchi (Abror Shopulatov). Public LEADERBOARD.md numbers; repository MIT covers software and documentation, no separate results licence stated and none asserted.